DesktopCommander and Taskmaster are great to start with. With just these, you may start to see why OP recommends a memory MCP too (I don’t have a recommendation for that yet)
Nice to see new things. Does your team know about SwarmUI[1]?
SwarmUI has been nice for sharing workflows with friends who might not want to learn ComfyUI, they can type in a prompt or any other config exposed in the workflow and even upload image input. It’s pretty good.
I would still like to see a web interface for workflows that is more so built for indie hackers. I’d like to see a Next.js frontend that calls ComfyUI on a server, it has a specific workflow configured for that app, and the server could be reused for another Next.js frontend, all that needs to change is the workflow. Letting you create multiple web apps with 1 Comfy backend.
Hey, thanks for sharing! I used it before and it is indeed useful for that kind of use case.
Like you said, there seems to be a gap between people who can use Comfy as a development tool and workflows' target users. The idea is to develop a set of tools to help bridge that gap.
Yes, I just used GPT-4 to create a prompt for GPT-3.5-Turbo based on some loose rules that I laid out. It helped me fill in the gaps and write it in a concise format.
The prompt gave much much better results than than the one I wrote.
I know there are other options, but here's the relevance:
"Go, also known as Golang, is recognized for its simplicity, efficiency, and cross-platform capabilities. Its ease of use has made it an attractive choice for malware authors seeking to create versatile and sophisticated threats."
They also mention it's a "growing trend in malware development"
Since Go binaries internally look different than "normal" binaries you see on Windows, it's really easy for the anti-virus systems to write signatures that basically trigger on all Go binaries. It's one of the bigger annoyances with Windows Go development; you often need to exclude your build directories from your virus scanner.
The only real disadvantage it has for malware development is that all else being equal, smaller malware is better than larger malware that does the same thing, and Go binaries are not small. But if you have a case where you don't care about that, all the same features that make it desirable to "real" programmers are useful for malware programmers too.
Just from hearing this, I was about to say "you could say this about Rust as well, so why hasn't Rust also become more popular for writing malware?" But apparently it has.
How relevant is it being cross-platform given that a lot of malware exploits OS specific weaknesses? Although I suppose there's no reason to have a core malware with multiple exploits for multiple OSes.
There's usually cryptography libraries in multiple languages if the exploiter is trying to be really fancy, or as simple as a string prefix search for common blockchain wallet address prefixes if the malware writer wants to be a bit lazier and save some time. So I tend to agree with the other user, this could have been done in just about any language (if not any language) so calling out Go just seems like a pointless finger-pointing at Go.
